High-voltage switch cabinet partial discharge fault identification method

By combining a multi-physics sensor array and a cascaded deep learning network, along with dynamic simulation coherent localization and a Bayesian risk network, the problems of shallow multi-modal information fusion and limited localization accuracy in partial discharge detection of high-voltage switchgear are solved. This achieves accurate identification and proactive early warning, and improves the robustness and interpretability of the system.

CN121522447APending Publication Date: 2026-02-13东阳中天电气科技有限公司
11 Cites 3 Cited by

Patent Information

Application Number
CN202512049630.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-31
Publication Date
2026-02-13

AI Technical Summary

Technical Problem

Existing technologies for partial discharge detection in high-voltage switchgear suffer from shallow multimodal information fusion, limited discharge source location accuracy due to ideal models, and a lack of forward-looking risk assessment, resulting in limited identification capabilities, large location errors, and poor system interpretability.

Method used

By employing a multi-physics sensor array to synchronously acquire signals, combined with a cascaded deep learning network and a dynamic simulation coherent localization method, deep fusion analysis and precise three-dimensional localization of multi-modal signals are achieved. Furthermore, a Bayesian risk network is used for fault assessment and early warning.

Benefits of technology

It achieves accurate identification and centimeter-level positioning of complex discharge modes, has forward-looking early warning capabilities, improves the interpretability and generalization ability of the system, and ensures high reliability and data privacy protection in high-noise environments.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a high-voltage switch cabinet partial discharge fault identification method and a storage medium. The method comprises the following steps: synchronously acquiring acoustic, electric, magnetic and thermal signals through a multi-physical field sensor array; performing preprocessing and feature extraction on the signals; using a cascade deep learning network to fuse multi-modal features to identify fault types and levels; realizing accurate positioning of the discharge source in the digital twinborn model by adopting a dynamic simulation coherent positioning method; and risk assessment and early warning are carried out by integrating diagnosis and positioning results. According to the method, deep learning and physical mechanism simulation are deeply fused through a data and model dual-drive normal form, so that the defects of shallow fusion level, low positioning precision, lack of interpretability and the like in the prior art are overcome, and intelligent, precise and prospective identification and early warning of the partial discharge fault of the high-voltage switch cabinet are realized.
Need to check novelty before this filing date? Find Prior Art